datasource-creator

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates the creation and validation of Datex Studio datasources. All operations use the vendor's CLI tool and are consistent with professional development workflows.
  • [COMMAND_EXECUTION]: The skill provides numerous templates for executing dxs commands. These commands are necessary for the skill's functionality and are targeted at the vendor's platform APIs.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. 1. Ingestion points: Requirements brief from conversational context (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Command execution via dxs, file writing, and network operations for datasource upsert (SKILL.md). 4. Sanitization: Absent. This is an architectural risk common to modular agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 07:45 PM